JP5867619B2 - Blast furnace abnormality detection method and blast furnace operation method - Google Patents

Description

  The present invention relates to a blast furnace anomaly detection method for detecting an anomaly in a blast furnace tuyere section, and a blast furnace operation method using the same.

  As a conventional blast furnace operating method, for example, there is a technique described in Patent Document 1. This technology counts the number of drops of unmelted ore from above at the tuyere, and the ratio of the ore and coke in the peripheral part charged from the top of the furnace so that the number of drops is below a preset reference value. Is to adjust. Here, a camera is installed in the blast furnace tuyere, and the number of unmelted ore drops is counted on the monitor, or the number of times the brightness in the image is reduced is counted as the number of unmelted ore drops.

Japanese Patent Laid-Open No. 5-186811

  However, the technique described in Patent Document 1 detects the fall of unmelted ore in the tuyere, and does not detect an abnormality in which the tuyere is blocked by the inflow of slag, hot metal, or the like. . In addition, since only a decrease in the luminance in the image is determined, it is not possible to detect a sudden luminance change when the tuyere is closed, separated from a gradual luminance change due to a temperature change in the raceway portion.

  Then, this invention makes it a subject to provide the blast furnace abnormality detection method which can detect the abnormality which becomes a tuyere obstruction | occlusion state at an early stage, and the blast furnace operation method using the same.

  In order to solve the above problems, one aspect of a blast furnace abnormality detection method according to the present invention is a blast furnace abnormality detection method for detecting an abnormality in which a tuyere part of a blast furnace is in a closed state, provided in the tuyere part. When the raceway part is imaged through the in-furnace monitoring window, the brightness of the captured image is less than or equal to a preset brightness threshold value, and the brightness reduction rate is less than or equal to a preset brightness reduction rate threshold value, the feathers It is characterized in that it is determined that an abnormality has occurred in which the mouth is blocked.

  In this way, since the luminance reduction rate is also determined in addition to the luminance decrease, it is possible to perform abnormality determination by separating the luminance change due to the gradual temperature change of the raceway portion and the abrupt luminance change at the time of closing the tuyere. .

  Further, in the above, the time when the luminance is equal to or lower than the luminance threshold from the time when the luminance of the captured image is equal to or lower than the luminance threshold and the luminance decrease rate is equal to or lower than the luminance decrease rate threshold. When continuing, it is preferable to determine that an abnormality occurs in which the tuyere is closed.

  The reason for this is that unmelted ore falls and sticks to the tip of the tuyere. This is because it may not be necessary. Thereby, a temporary tuyere occlusion state can be excluded from an abnormality detection target, and only a more serious occlusion state can be detected.

  Furthermore, in the above, it is preferable to calculate the luminance reduction rate using a least-square method based on the past luminance data of a plurality of points.

  Thereby, an average luminance change rate is obtained. Therefore, even when the luminance change of the raceway portion is severe between the current time and one sampling before, an appropriate luminance change rate can be obtained without being affected by the vertical movement. Therefore, overdetection of abnormality can be suppressed.

  In the above, it is preferable that the luminance threshold value is set to a value smaller than the average value by a certain percentage with reference to the average value of the luminance data of a plurality of past points.

  In this way, since the luminance threshold is set based on the average value of past luminance data, it is possible to appropriately detect a decrease in luminance even when the luminance is generally low.

  Moreover, one aspect of the blast furnace operating method according to the present invention is characterized in that when an abnormality is detected using any one of the above-described blast furnace abnormality detection methods, the amount of air blown to the tuyere is adjusted.

  As described above, when an abnormality that causes the tuyere to be closed is detected, it is possible to adjust operation conditions such as increasing or decreasing the amount of air blown to the tuyere. Therefore, it is possible to appropriately carry out the abnormal process, and to realize stable blast furnace operation.

  According to the present invention, it is possible to detect only a sudden decrease in luminance separately from a gradual decrease in luminance due to a temperature change in the raceway portion. Thereby, the abnormality which becomes a tuyere obstruction | occlusion state can be detected with high accuracy early.

  In addition, since the operating conditions are adjusted when it is determined that the above abnormality has occurred, it is possible to avoid a serious situation such as a blowout of material in the furnace from the tuyere, and to improve safety and equipment repair costs. The effect is obtained.

FIG. 1 is an overall view of a blast furnace to which the blast furnace operating method of the present embodiment is applied. FIG. 2 is a diagram showing the installation position of the camera. FIG. 3 is a diagram illustrating an example of an image captured by the camera. FIG. 4 is a flowchart showing an abnormality detection processing procedure. FIG. 5 is a diagram showing a change in luminance over time including an unmelted ore falling phenomenon. FIG. 6 is a diagram showing a change in luminance over time that does not include the unmelted ore falling phenomenon. FIG. 7 is a diagram illustrating the luminance change rate. FIG. 8 is a diagram showing a luminance change and a luminance threshold over time including an unmelted ore falling phenomenon. FIG. 9 is a diagram showing a result of time abnormality determination including an unmelted ore falling phenomenon. FIG. 10 is a diagram illustrating a luminance change and a luminance threshold during a time period that does not include the unmelted ore falling phenomenon. FIG. 11 is a diagram illustrating an abnormality determination result of a time that does not include the unmelted ore falling phenomenon. FIG. 12 is a flowchart illustrating an abnormality detection processing procedure according to the second embodiment. FIG. 13 is a diagram illustrating an abnormality determination result of a time including an unmolten ore falling phenomenon in the second embodiment.

Hereinafter, embodiments of the present invention will be described with reference to the drawings.
(First embodiment)
FIG. 1 is an overall view of a blast furnace to which the blast furnace operating method of the present embodiment is applied.
As shown in FIG. 1, a blower pipe (blow pipe) 3 for blowing hot air from a hot stove is connected to the inside of the tuyere 2 of the blast furnace 1 and penetrates through the blower pipe 3. The lance 4 is installed. From the lance 4, fuel such as pulverized coal, oxygen and city gas is blown into the furnace.

  A combustion space called a raceway 5 exists in the coke deposit layer in front of the tuyere 2 in the direction of blowing hot air, and coke combustion and gasification (reduction of iron ore, that is, ironmaking) are mainly performed in this combustion space. .

  Further, as shown in FIG. 2, an in-furnace monitoring window 6 is formed at the tuyere for the operator to monitor the inside of the furnace. A camera 11 for imaging the raceway 5 through the in-furnace monitoring window 6 is installed in the vicinity of the in-furnace monitoring window 6.

  FIG. 3 is a diagram illustrating an example of an image captured by the camera 11. As shown in FIG. 3, the captured image shows the silhouette of the raceway 5 and the lance 4 inside the circular shape corresponding to the tip opening of the small tuyere 2 a constituting the tuyere 2.

  A captured image of the raceway section captured by the camera 11 is input to the abnormality detection section 12. The anomaly detection unit 12 detects an anomaly such that the tuyere 2 is blocked using the captured image captured by the camera 11.

  The unmelted ore falls when the raceway 5 is destroyed. At this time, a part of unmelted ore may adhere to the tip of the tuyere 2 and the tuyere 2 may be closed. Moreover, this tuyere closed state can also occur when slag, hot metal, or the like flows in. And when it becomes a tuyere obstruction | occlusion state, the phenomenon in which the brightness | luminance in a captured image falls rapidly arises.

  Therefore, the abnormality detection unit 12 detects an abnormality that causes the tuyere closed state by monitoring a phenomenon in which the brightness of the image inside the tuyere suddenly decreases. The detection result by the abnormality detection unit 12 is displayed on the monitor 13 and notified to the operator.

  The abnormality detection result by the abnormality detection unit 12 is also input to the operation condition adjustment unit 14. When the abnormality detection unit 12 detects an abnormality that causes the tuyere closed state, the operation condition adjustment unit 14 adjusts the blast furnace operation conditions such as increasing or decreasing the amount of hot air blown into the furnace.

  FIG. 4 is a flowchart showing an abnormality detection processing procedure executed by the abnormality detection unit 12. This abnormality detection process is repeatedly executed every predetermined time. First, in step S <b> 1, the abnormality detection unit 12 acquires a captured image captured by the camera 11.

  Next, in step S2, the abnormality detection unit 12 selects the maximum luminance in the image for the captured image (grayscale) acquired in step S1, and uses this as the representative value (representative luminance) of the luminance in the image. To do.

  Next, in step S3, the abnormality detection unit 12 obtains a change rate (luminance change rate) of the representative brightness using the time series data of the representative brightness selected in step S2. Here, a straight line fitted by the least square method using a plurality of past (M points) data is obtained, and the inclination of the straight line is adopted as the luminance change rate.

  Next, in step S4, the abnormality detection unit 12 determines whether or not the luminance change rate calculated in step S3 is equal to or less than a preset threshold value R. Here, the threshold value R is a negative value, and is set to −10, for example. That is, here, it is determined whether or not the luminance reduction rate is equal to or less than a preset luminance reduction rate threshold. When it is determined that the luminance change rate is equal to or less than the threshold value R, the process proceeds to step S5.

  In step S5, the abnormality detection unit 12 determines whether or not the representative luminance (maximum luminance) selected in step S2 is equal to or less than a preset threshold (luminance threshold) S. Here, for example, the threshold value S is set to a value (for example, a value obtained by multiplying 0.7) that is smaller than the result obtained by taking the moving average with respect to the representative luminance acquired in the past predetermined time (for example, 10 minutes). And when it determines with it being below the threshold value S, it transfers to step S6.

  In step S <b> 6, the abnormality detection unit 12 ends the abnormality detection process after determining that an abnormality in which the tuyere is closed (abnormality detection) has occurred.

  On the other hand, if it is determined in step S4 that the luminance change rate is higher than the threshold value R, or if it is determined in step S5 that the representative luminance is higher than the threshold value S, the process proceeds to step S7. The abnormality detection process is terminated after determining that no occurrence (abnormality non-detection) has occurred.

  Hereinafter, the abnormality detection process in the tuyere will be described using a specific example.

  First, the abnormality detection unit 12 first acquires a captured image of the raceway unit captured by the camera 11 installed in the specific tuyere 2 (step S1 in FIG. 4), and then the maximum luminance in the acquired captured image. Is selected (step S2).

  At this time, the time series data of the maximum brightness in the time including the phenomenon that the unmolten ore falls is as shown in FIG. The data in FIG. 5 is the maximum luminance data for 60 seconds acquired at the sample period of 0.3 seconds. In addition, the luminance here is a grayscale image captured by the camera 11 and represented by 256 gradations between white and black. As shown in the portion surrounded by the broken line A in FIG. 5, the luminance rapidly decreases during the time when the unmelted ore falls. On the other hand, the time series data of the maximum brightness in a time period that does not include a phenomenon in which unmelted ore falls is as shown in FIG. When the unmelted ore falling phenomenon is not included, the luminance in the image changes gently as a whole due to the temperature change of the raceway 5 or the fogging of the glass separating the inside of the furnace and the camera 11.

  Thus, even if the unmelted ore has not fallen, the luminance is reduced. For this reason, if threshold processing is applied only to a decrease in luminance to determine an abnormality that results in a closed tuyere, a gradual decrease in luminance due to a temperature change in the raceway portion is also detected as an abnormality at the same time. Therefore, it is not possible to accurately detect a luminance decrease phenomenon that leads to the closing of the tuyere 2 due to overdetection. Therefore, in the present embodiment, abnormality determination is performed by performing threshold processing on the luminance change rate in addition to threshold processing on luminance reduction. That is, it is determined that the luminance reduction phenomenon that leads to the closing of the tuyere 2 occurs only when the luminance is reduced and the luminance reduction rate is small.

  At this time, as the rate of change in luminance, the slope of a straight line when straight fitting is performed by the least square method on the maximum luminance data at the past M points is adopted.

  By the way, as a method for obtaining the luminance change rate, the simplest method is to take a difference between the current data and the data one point before (one sampling before). The symbol a in the lower part of FIG. 7 is a result of obtaining the luminance change rate by a method of taking a difference based on the luminance change in the upper part of FIG.

  In this way, when the difference is used, if the luminance change at each time is severe, the luminance change rate also changes drastically. Therefore, as shown in the portion surrounded by the symbol B, it is impossible to capture the luminance change when the unmelted ore falling phenomenon surrounded by the symbol A occurs. That is, when the difference is adopted as the luminance change rate, it is difficult to detect only a target luminance decrease.

  On the other hand, when the slope of the straight line when the straight line fitting is performed by the least square method is adopted as the luminance change rate, the luminance change rate is as indicated by symbol b in the lower part of FIG. In this case, it is possible to suppress the influence of a fine luminance change with a short cycle, and as shown in the part surrounded by the symbol B, the luminance change at the time of occurrence of the unmelted ore falling phenomenon surrounded by the symbol A is accurately captured. be able to.

  Therefore, the abnormality detection unit 12 performs threshold processing on the representative luminance (maximum luminance) in the captured image and the luminance change rate calculated using the least square method. Then, when it is determined that the representative luminance and the luminance change rate are equal to or less than the respective threshold values S and R (Yes in Step S4 and Yes in Step S5), a sudden decrease in luminance that can cause the tuyere closed state occurs. (Step S6).

  Here, the threshold value S is a value that is smaller than the moving average value by a certain percentage on the basis of the moving average value of luminance data at a plurality of points in the past (for example, the threshold S is in a range of 30% to 70% of the moving average value). Value). The time average brightness at the current time is determined by the temperature of the raceway section. On the other hand, when the tuyere is blocked, the luminance decreases with respect to the luminance at the current time. For this reason, if a decrease in luminance is determined using a certain threshold value, a decrease in luminance phenomenon cannot be detected if a tuyere blockage occurs from a state having an average luminance equal to or less than the threshold value S. Therefore, by setting the threshold value S as a dynamic value, it is possible to appropriately detect a sudden decrease in luminance even when the luminance is low as a whole.

  Then, when the above abnormality determination is performed on the luminance data including the unmelted ore falling phenomenon shown in FIG. 5, the representative luminance is equal to or lower than the threshold value S at time t1 in FIG. Become. Therefore, in this case, as shown in FIG. 9, it is determined that abnormality is detected (= 1) at time t1.

  On the other hand, when the abnormality determination is performed on the luminance data that does not include the unmelted ore falling phenomenon shown in FIG. 6, the representative luminance becomes equal to or less than the threshold value S according to the temperature change of the raceway portion as shown in FIG. In some cases, the luminance change rate at that time does not fall below the threshold value R. Therefore, as shown in FIG. 11, it is determined that abnormality is not detected (= 0).

  As described above, in this embodiment, since the raceway unit is imaged by the camera 11 and threshold processing is performed on the luminance and the luminance change rate in the captured image, the luminance change due to the gradual temperature change of the raceway unit. Thus, it is possible to make an abnormality determination by separating a sudden change in luminance when the tuyere is closed.

  At this time, since a straight line fitted by the least square method is obtained using a plurality of luminance data of the past M points, and the slope of the straight line is adopted as the luminance change rate, the data is averaged and stable for threshold processing. The luminance change rate can be obtained.

  In the threshold processing for luminance, a value of a certain ratio with respect to average luminance using past luminance data is set as a threshold. Thus, abnormality determination accuracy can be improved by dynamically setting the threshold value.

  Furthermore, since the maximum luminance in the captured image is set as the representative luminance and the threshold processing is performed using the representative luminance, the signal processing can be speeded up. In addition, since the area of the tip opening of the small tuyere 2a in the captured image varies depending on individual differences for each tuyere, the attachment state of the camera 11, and the like, for example, the average luminance in the captured image is greatly influenced by the black portion of the silhouette. Although it is inappropriate as the representative luminance, the change in the luminance in the image can be appropriately monitored by setting the representative luminance to the maximum luminance in the captured image as in the present embodiment.

  In addition, when an abnormality that causes a tuyere blockage is detected, the amount of hot air blown is increased to remove unfused ore stuck to the tip of the tuyere, or the amount of hot air blown is reduced to increase safety. The operating conditions can be adjusted, such as securing.

  In this way, the tuyere blockage phenomenon can be detected at an early stage and the abnormal treatment can be appropriately performed, so that it is possible to prevent serious accidents such as ejection of objects in the furnace from the tuyere, safety and equipment Effective in terms of repair costs.

(Second Embodiment)
Next, a second embodiment of the present invention will be described.

  In the second embodiment, the duration of the luminance decrease is added to the evaluation when the abnormality is determined.

  FIG. 12 is a flowchart illustrating an abnormality detection processing procedure executed by the abnormality detection unit 12 according to the second embodiment. This abnormality detection process is the same as the abnormality detection process of FIG. 4 except that the process of step S11 is added. Therefore, here, the description will focus on the different parts of the processing.

  In step S11, the abnormality detection unit 12 determines whether or not the time during which the luminance is equal to or less than the threshold value S continues for a certain time T. The fixed time T is a time in which the action change of the blast furnace operation after the abnormality detection is in time, and is set between several seconds to about 10 minutes, and here, for example, 10 seconds.

  If it is determined that the time during which the luminance is equal to or less than the threshold S has not reached the predetermined time T, the process proceeds to step S5. If it is determined that the predetermined time T has been reached, the process proceeds to step S6.

  Thereby, for example, when unmelted ore falls and temporarily becomes a tuyere closed state, the luminance is equal to or lower than the threshold value S and the luminance change rate is equal to or lower than the threshold value R at time t1 in FIG. Before the fixed time T elapses, the unmelted ore is peeled off from the tuyere and the luminance exceeds the threshold value S, so that it is judged that no abnormality that causes the tuyere closed state has occurred. That is, as shown in FIG. 13, the abnormality determination result is abnormality non-detection (= 0), and the phenomenon that unmelted ore falls in a short time can be excluded from the abnormality detection target.

  When the unmelted ore fall phenomenon sticks to the tip of the small tuyere 2a for a long time, the tuyere is blocked, but the normal unmelted ore fall may fall down in a short time, so it may be excluded from the abnormality detection target. Many. After the luminance and the luminance change rate are equal to or less than the respective threshold values S and R, the tuyere is reliably closed only by determining that the abnormality occurs only when the time when the luminance is equal to or less than the threshold value S continues for a certain time T. It is possible to detect only the case.

  In this way, the undetected ore falling phenomenon that falls in a short time with a small contribution to a serious accident can be excluded from the judgment, so that overdetection can be suppressed, and it is not necessary to take unnecessary operation actions, thereby reducing the operation cost. .

(Modification)
In each of the above embodiments, the case where the luminance change rate is obtained using the least square method has been described. However, any method that can obtain an average luminance change rate can be used instead.

DESCRIPTION OF SYMBOLS 1 Blast furnace 2 tuyere 3 Fan pipe 4 Lance 5 Raceway 6 Furnace monitoring window 11 Camera 12 Abnormality detection part 13 Monitor 14 Operation condition adjustment part

Claims (5)

A blast furnace abnormality detection method for detecting an abnormality in which the tuyere of the blast furnace becomes blocked,
The raceway unit is imaged through the furnace monitoring window provided in the tuyere, the luminance of the captured image is equal to or less than a preset luminance threshold, and the luminance reduction rate is a preset luminance reduction rate threshold Blast furnace abnormality detection characterized in that when the time during which the luminance is equal to or less than the luminance threshold value has continued for a certain period of time from the time when the luminance becomes below , an abnormality that causes the tuyere to become blocked is occurring. Method. In the blast furnace abnormality detection method according to claim 1 ,
A method for detecting an abnormality in a blast furnace, wherein the luminance reduction rate is calculated using a least square method based on past brightness data of a plurality of points. In the blast furnace abnormality detection method according to claim 1 or 2,
A method for detecting an abnormality in a blast furnace , wherein the luminance threshold value is a dynamic value based on a moving average value of luminance data of a plurality of past points . In the blast furnace abnormality detection method according to claim 1 or 2 ,
A method for detecting an abnormality in a blast furnace, wherein the luminance threshold value is set to a value smaller than the moving average value by a certain percentage with reference to a moving average value of luminance data of a plurality of past points. A blast furnace operating method, wherein an abnormality is detected by using the blast furnace abnormality detection method according to any one of claims 1 to 4, and an amount of air blown to the tuyere is adjusted.

Images